AlibabaQwen3.8
Qwen3.8 Max
Qwen3.8 Max accepts text, images and video. Model Studio lists a one-million-token context and 128,000-token output limit.
Technical details
It supports thinking, function calls, built-in tools and structured output.Model Studio text generation models
Practical use
Practical guidance. Choose Max when a task combines extensive source material with visual evidence. Keep the tool execution log separate from the final answer so reviewers can trace which actions produced a result.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Model identifiers | qwen3.8-max |
| Access | Hosted Model Studio API.Model Studio text generation models |
Related models
- Qwen3.8-27B
Alibaba · Qwen3.8
Dense 27-billion-parameter vision-language model with weights released under Apache 2.0.
Launch date not confirmedDownloadable - Qwen3.8-2.4T-A95B
Alibaba · Qwen3.8
Text-only mixture-of-experts model with 2.4 trillion total parameters and 95 billion active parameters.
Launch date not confirmedDownloadable